© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55301
    Prev
    Next
    INDEX
    Explanations

    probability questions with counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergarten
    -0.10
    äll
    -0.09
    fait
    -0.09
    hare
    -0.09
    isp
    -0.09
    ocard
    -0.09
     double
    -0.09
    quartered
    -0.09
    ATA
    -0.08
    -alt
    -0.08
    POSITIVE LOGITS
     missing
    0.07
    agli
    0.07
     Synd
    0.07
    _tc
    0.07
     BCH
    0.07
     Gross
    0.07
     Quant
    0.07
     inclusive
    0.07
    urs
    0.07
     Acceler
    0.07
    Activations Density 0.001%

    No Known Activations